Finish rolling roller change fuzzy matching control method and system

Abstract

The invention provides a finish rolling roller changing fuzzy matching control method and system, and the method comprises the steps: matching a roller changing learning value from a roller changing learning data table when a first strip steel is subjected to finish rolling preset calculation after a working roller is changed in finish rolling, the roll changing learning data table is used for recording various preset learning values of finish rolling of the first strip steel after roll changing; and according to the matched roll changing learning value, finish rolling presetting calculation of the first strip steel after finish rolling roll changing is carried out, so that the accuracy of finish rolling presetting parameters of the first strip steel after finish rolling roll changing and rolling is carried out is improved. The method can effectively improve the control precision of the head thickness of the first block during finish rolling roll-changing rolling, and solves the problem of large control deviation of the head thickness of the first block during roll-changing rolling.

Description

Technical Field

[0001] This invention relates to the field of steel production application technology, and in particular to a fuzzy matching control method and system for finishing mill roll changing. Background Technology

[0002] In the hot strip steel production process, the actual rolling force of the finishing strip is directly and strongly correlated with the deformation temperature and deformation speed. Traditional pre-set models are difficult to use the same set of rolling force parameters to meet a wide range of temperature and rolling speed changes. Furthermore, the existing control technology does not have a separate control strategy for the first section of finishing strip rolling after roll change, resulting in low pre-set accuracy of the first section of finishing strip rolling after roll change. The final rolling temperature and thickness deviation of the first section of finishing strip rolling after roll change are relatively large, which affects the quality control accuracy of the head and the entire length of the coil after roll change. Summary of the Invention

[0003] This invention provides a fuzzy matching control method and system for finishing mill roll changing to solve the technical problem of large deviations in the final rolling temperature and thickness of the first roll head during roll changing.

[0004] This invention provides a fuzzy matching control method for finishing mill roll changing, the method comprising:

[0005] When calculating the pre-set values ​​for the first strip after the finishing mill roll change, the roll change learning values ​​are matched from the roll change learning data table, wherein the roll change learning data table is used to record various learning values ​​for the pre-set values ​​for the first strip after the roll change. The pre-setting calculation of the finishing mill for the first strip after the finishing mill roll change is performed based on the matched roll change learning value, so as to improve the accuracy of the pre-setting parameters of the finishing mill for the first strip after the finishing mill roll change.

[0006] In one embodiment of the present invention, when no corresponding roll change learning value is found in the roll change learning data table, the matching range of the heating furnace and the roughing mill exit temperature layer is widened to a preset range to obtain the corresponding roll change learning value, which is used for the pre-set calculation of the first strip after the finishing mill roll change.

[0007] In one embodiment of the present invention, if the matching range of the heating furnace and the roughing mill exit temperature layer is widened to a preset range and the corresponding roll change learning value is still not matched, the corresponding roll change learning value is matched from the long-cycle data table, wherein the long-cycle data table is used to record various learning values ​​of finishing mill calculated after finishing milling.

[0008] In one embodiment of the present invention, if the corresponding roll change learning value is not matched in the long-cycle data table, the conventional learning value is used to perform the pre-setting calculation of the first strip after the roll change in the finishing mill.

[0009] In one embodiment of the present invention, the roll change learning data table and the long-cycle data table store data by associating roll change learning values ​​with primary keys. When matching roll change learning values, the corresponding roll change learning value is queried by matching the primary key. The primary key includes heating furnace layer, roughing mill exit temperature layer, rolling grade, steel tapping mark, thickness layer, width layer, whether the hot coil box is used layer, and target final rolling temperature layer.

[0010] In one embodiment of the present invention, querying the corresponding roll-changing learning value by matching the primary key includes: firstly matching all primary keys in the roll-changing learning data table to obtain an exact matching result for the roll-changing learning value; if no exact matching result exists, then widening the matching range of the heating furnace and roughing mill exit temperature layers to a preset range, and then matching all primary keys in the roll-changing learning data table to obtain a fuzzy matching result for the roll-changing learning value. The present invention also provides a finishing mill roll-changing fuzzy matching control system, the system comprising: The data matching module is used to match the roll change learning value from the roll change learning data table when calculating the pre-set finishing of the first strip after the work roll change in the finishing mill. The roll change learning data table is used to record various learning values ​​for the pre-set finishing of the first strip after the roll change. The roll changing setting module is used to perform pre-setting calculations for the finishing of the first strip after the finishing roll change based on the matched roll changing learning values, so as to improve the accuracy of the pre-setting parameters for the finishing of the first strip after the finishing roll change.

[0011] The beneficial effects of this invention are as follows: The fuzzy matching control method and system for finishing mill roll changing proposed in this invention provide a separate roll changing learning data table for the first strip after the finishing mill roll change. This table records various learning values ​​for the finishing mill rolling of the first strip after the roll change. During each finishing mill roll change, the learning values ​​are matched from this roll changing learning data table and used for the pre-setting calculation of the finishing mill rolling of the first strip after the roll change. This improves the accuracy of the pre-setting calculation of the finishing mill rolling of the first strip after the roll change, thereby reducing the control deviation of the final rolling temperature and thickness of the strip head after the roll change, effectively improving the head thickness control accuracy, and ensuring the quality of the product after the roll change. Attached Figure Description

[0012] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0013] In the attached diagram: Figure 1 This is a flowchart illustrating the fuzzy matching control method for finishing mill roll changing in one embodiment of the present invention; Figure 2 This is a schematic diagram of the configuration file corresponding to the fuzzy matching function provided in one embodiment of the present invention; Figure 3 This is a block diagram of a fuzzy matching control system for finishing mill roll changing provided in one embodiment of the present invention. Detailed Implementation

[0014] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0015] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. The drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0016] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0017] Please see Figure 1 , Figure 1 This is a flowchart illustrating a fuzzy matching control method for finishing mill roll changing in one embodiment of the present invention. The method includes the following steps: Step S100: When calculating the pre-set values ​​for the first strip after changing the work roll in the finishing mill, the roll changing learning values ​​are matched from the roll changing learning data table. The roll changing learning data table is used to record various learning values ​​for the pre-set values ​​of the first strip after the roll changing.

[0018] In one embodiment, a separate roll-changing learning data table and a long-cycle data table can be set up. The roll-changing learning data table records various learning values ​​for the finishing of the first strip after roll changing, including finishing temperature, rolling force, and roll gap learning values. The long-cycle data table records various learning values ​​calculated after finishing. The learning values ​​in the long-cycle data table are finishing self-learning parameters indicating that the head quality meets requirements during the historical rolling process for different steel grades and specifications. These values ​​are typically stored for a long time and are not frequently updated or changed. In both the roll-changing learning data table and the long-cycle data table, learning values ​​are stored with a primary key, which serves as the table index. The primary key can be divided into eight layers: heating furnace layer, roughing mill exit detection temperature layer, steel grade, tapping mark, thickness layer, width layer, hot coil box usage layer, and target final rolling temperature layer. Unlike existing conventional learning methods, this method adds new layers for steel grade and intermediate billet inlet temperature (RDT) (i.e., the roughing mill exit temperature range layer). The heating furnace is also included as a primary key for classification. Furthermore, the RDT of the roughing mill intermediate billet inlet temperature can be categorized into eight classes with intervals of 960.0, 980.0, 1000.0, 1020.0, 1040.0, 1060.0, and 1080.0 in the corresponding data table. A layer is defined as less than or equal to 960, a layer is defined as greater than 1080, and the intervals are defined as greater than the left layer and less than or equal to the right layer. In subsequent queries, the corresponding temperature layer learning value can be added to the roughing mill intermediate billet inlet temperature query data table for precise matching. If no matching data is found in the precise query, the query range can be expanded to adjacent layers to obtain corresponding fuzzy matching results.

[0019] In one embodiment, during the pre-set calculation for the start of the finishing mill roll change, a fuzzy matching query function can be activated. This function uses relevant information about the finished strip, such as thickness, target final rolling temperature, width, tap mark, and rolling grade, as input and matches it against corresponding indices in a data table. When the similarity to the index reaches a set threshold, it is determined that matching data exists in the data table, and the various learned values ​​indexed from the data table are output. A separate configuration file, FSUINHERIT.conf, can be generated for the finishing mill roll change fuzzy matching function. This configuration file is as follows: Figure 2 As shown, the preset input mode for the first strip after changing work rolls in the finishing mill can be represented as input.mode 01, and the output mode can be represented as output.mode 01. By modifying the input and output modes in the configuration file, the fuzzy matching function can be applied to the pre-set calculation process for the first strip after the roll change.

[0020] In one embodiment, for the first strip to be rolled during the finishing mill roll change, a separate `rollchange` table (i.e., the roll change learning data table) is queried (input mode `intput.mode==01`). First, an exact match is performed (matching the aforementioned 8 primary keys). If no exact match is found, a fuzzy match is performed with a relaxed heating furnace and RDT temperature range of ±1. If the fuzzy match still fails to find a match, an exact match is performed on the long-cycle data table. If no match is found in the long-cycle data table, conventional learning values ​​are used for the pre-set calculations of the finishing mill. Conventional learning values ​​may include finishing mill rolling force learning values, roll gap learning values, and temperature learning values. The finishing mill rolling force learning values ​​and roll gap learning values ​​are updated after finishing milling based on the tap mark, thickness, width, and final rolling temperature layer (when measured data of the strip head is collected after finishing milling). The finishing mill temperature learning value is updated after finishing milling based on the tap mark, thickness, width, target final rolling temperature, and heating furnace layer.

[0021] Step S110: Perform the pre-setting calculation of the finishing rolling of the first strip after the finishing roll change based on the matched roll change learning value, so as to improve the accuracy of the pre-setting parameters of the finishing rolling of the first strip after the finishing roll change starts rolling.

[0022] In one embodiment, when no corresponding roll change learning value is found in the roll change learning data table, the matching range of the heating furnace and roughing mill exit temperature is widened to a preset range to obtain the corresponding roll change learning value, which is used for the pre-setting calculation of the first strip after the finishing mill roll change. Specifically, when no exact matching data is found through matching all primary keys, fuzzy matching can be performed only for the two layers of heating furnace number and roughing mill exit temperature. For example, the layer matching range of the roughing mill exit temperature detection can be widened to the left layer or the right layer. The result of the fuzzy matching is used for the pre-setting calculation of the first strip after the roll change to improve the pre-setting accuracy of the first strip after the finishing mill roll change and avoid excessive deviations in the final rolling temperature and thickness of the first strip after the roll change.

[0023] In one embodiment, if the matching range of the heating furnace and roughing mill exit temperature levels is widened to a preset range, and the corresponding roll change learning value is still not matched, then the corresponding roll change learning value is matched from the long-cycle data table. The long-cycle data table records various learning values ​​for finishing milling calculated after finishing milling. If the corresponding roll change learning value is still not matched from the long-cycle data table, then the conventional learning value is used for the pre-setting calculation of the finishing milling of the first strip after the finishing mill roll change. The specific process can be represented as follows: After the finishing mill roll change, the first strip is rolled. A separate `rollchange` table is queried (input mode `intput.mode==01`). First, an exact match value is performed (matching the above 8 primary keys). If no exact match value is found, only data matching with a wider range of ±1 levels of the heating furnace and roughing mill exit RDT temperature is performed. If no match is found, an exact match is performed from the long-cycle data table (matching all primary keys in the long-cycle data table). If no match is found again, the conventional self-learning value is used for the pre-setting calculation of the finishing milling. The regular self-learning values ​​are updated based on primary keys such as the steel tapping mark, thickness, width, and target final rolling temperature, and are recorded and stored in a separate regular data table.

[0024] Based on the above technical solution of the present invention, by optimizing the logic of the learning value of the finishing mill during the pre-setting calculation of the first strip of steel after the finishing mill roll change, the problem of large head thickness control deviation of the first strip of steel after the finishing mill roll change is solved, which effectively improves the head final rolling temperature and thickness control accuracy of the first strip of steel after the finishing mill roll change, ensures the product quality index of the first strip of steel after the finishing mill roll change, and improves the stability of finishing mill rolling.

[0025] Please see Figure 3 In one embodiment, the present invention also provides a fuzzy matching control system for finishing mill roll changing, the system comprising: a data matching module 30, used to match roll changing learning values ​​from a roll changing learning data table when calculating the finishing mill pre-setting of the first strip after the finishing mill roll change, wherein the roll changing learning data table is used to record various learning values ​​for the finishing mill pre-setting of the first strip after the roll change; and a roll changing setting module 31, used to perform finishing mill pre-setting calculation of the first strip after the finishing mill roll change based on the matched roll changing learning values, so as to improve the accuracy of the finishing mill pre-setting parameters of the first strip after the finishing mill roll change.

[0026] In one embodiment, the data matching module 30 can also be used to widen the matching range of the heating furnace and roughing mill exit temperature layers to a preset range when no corresponding roll change learning value is matched in the roll change learning data table, so as to obtain the corresponding roll change learning value for the pre-set calculation of the first strip after the finishing mill roll change.

[0027] In one embodiment, the data matching module 30 can also be used to match the corresponding roll change learning value from the long-cycle data table when the matching range of the heating furnace and the roughing mill exit temperature layer is widened to a preset range but the corresponding roll change learning value is still not matched. The long-cycle data table is used to record various learning values ​​of finishing mill calculated after finishing milling.

[0028] In one embodiment, the data matching module 30 can also be used to perform the pre-setting calculation of the first strip after the finishing roll change using the conventional learning value if the corresponding roll change learning value is not matched in the long-cycle data table.

[0029] In one embodiment, the data matching module 30 can also be used to store data in the roll change learning data table and the long-cycle data table by associating the roll change learning value with the primary key. When matching the roll change learning value, the corresponding roll change learning value is queried by matching the primary key. The primary key includes the heating furnace layer, the roughing mill exit temperature layer, the rolling grade, the steel tapping mark, the thickness layer, the width layer, whether the hot coil box is used, and the target final rolling temperature layer.

[0030] In one embodiment, the data matching module 30 can also be used to query the corresponding roll-changing learning value by matching the primary key, including: firstly matching all primary keys in the roll-changing learning data table to obtain an exact matching result for the roll-changing learning value; if no exact matching result exists, then widening the matching range of the heating furnace and roughing mill exit temperature layers to a preset range, and then matching all primary keys in the roll-changing learning data table to obtain a fuzzy matching result for the roll-changing learning value. Since the system of this invention and the aforementioned method embodiments belong to the same inventive concept, the execution process of the system can be referred to the execution process of each step in the aforementioned method embodiments, and will not be repeated here.

[0031] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A fuzzy matching control method for finishing mill roll changing, characterized in that, The method includes: When calculating the pre-set values ​​for the first strip after the finishing mill roll change, the roll change learning values ​​are matched from the roll change learning data table, wherein the roll change learning data table is used to record various learning values ​​for the pre-set values ​​for the first strip after the roll change. The pre-setting calculation of the finishing mill for the first strip after the finishing mill roll change is performed based on the matched roll change learning value, so as to improve the accuracy of the pre-setting parameters of the finishing mill for the first strip after the finishing mill roll change.

2. The fuzzy matching control method for finishing mill roll changing according to claim 1, characterized in that, When no corresponding roll change learning value is found in the roll change learning data table, the matching range of the heating furnace and the roughing mill exit temperature layer is widened to a preset range to obtain the corresponding roll change learning value, which is used for the pre-set calculation of the first strip after the finishing mill roll change.

3. The fuzzy matching control method for finishing mill roll changing according to claim 2, characterized in that, If the matching range of the heating furnace and the roughing mill exit temperature layer is widened to a preset range, but the corresponding roll change learning value is still not matched, the corresponding roll change learning value is matched from the long-cycle data table, wherein the long-cycle data table is used to record various learning values ​​of finishing mill calculated after finishing milling.

4. The fuzzy matching control method for finishing mill roll changing according to claim 3, characterized in that, If the corresponding roll change learning value is not found in the long-cycle data table, the conventional learning value is used to perform the pre-setting calculation for the first strip after the roll change in the finishing mill.

5. The fuzzy matching control method for finishing mill roll changing according to claim 4, characterized in that, The roll change learning data table and the long-cycle data table store data by associating roll change learning values ​​with primary keys. When matching roll change learning values, the corresponding roll change learning value is queried by matching the primary key. The primary key includes heating furnace layer, roughing mill exit temperature layer, rolling grade, steel tapping mark, thickness layer, width layer, whether the hot coil box is used layer, and target final rolling temperature layer.

6. The fuzzy matching control method for finishing mill roll changing according to claim 5, characterized in that, Querying the corresponding roll change learning value by matching the primary key includes: firstly matching all primary keys in the roll change learning data table to obtain an exact matching result for the roll change learning value; if no exact matching result exists, the matching range of the heating furnace and roughing mill exit temperature layers is widened to a preset range, and then all primary keys in the roll change learning data table are matched to obtain a fuzzy matching result for the roll change learning value.

7. A fuzzy matching control system for finishing mill roll changing, characterized in that, The system includes: The data matching module is used to match the roll change learning value from the roll change learning data table when calculating the pre-set finishing of the first strip after the work roll change in the finishing mill. The roll change learning data table is used to record various learning values ​​for the pre-set finishing of the first strip after the roll change. The roll changing setting module is used to perform pre-setting calculations for the finishing of the first strip after the finishing roll change based on the matched roll changing learning values, so as to improve the accuracy of the pre-setting parameters for the finishing of the first strip after the finishing roll change.

Images